Proceedings ArticleDOI
A new method of text-independent speaker recognition
A. Higgins,R. Wohlford +1 more
- Vol. 11, pp 869-872
Reads0
Chats0
TLDR
A new method, based on template matching, that utilizes temporal information to advantage in text-dependent recognition as a special case and is compared with that of similar recently-developed methods.Abstract:
Text-independent speaker recognition methods have been based on measurements of long-term statistics of individual speech frames. These methods are not capable of modeling speaker-dependent speech dynamics. In this paper, we describe a new method, based on template matching, that utilizes temporal information to advantage. The template-matching method performs text-dependent recognition as a special case. Performance of the template-matching method is compared with that of similar recently-developed methods.read more
Citations
More filters
Journal ArticleDOI
Speaker recognition: a tutorial
TL;DR: A tutorial on the design and development of automatic speaker-recognition systems is presented and a new automatic speakers recognition system is given that performs with 98.9% correct decalcification.
Journal ArticleDOI
Neural network adaptive wavelets for signal representation and classification
TL;DR: The idea is introduced of a "super-wavelet," a linear combination of wavelets that itself is treated as a wavelet that allows the shape of the wavelet to adapt to a particular problem, which goes beyond adapting parameters of a fixed-shape wavelet.
Journal ArticleDOI
Recent advances in speaker recognition
TL;DR: Recent advances in speaker recognition technology include VQ- and ergodic-HMM-based text-independent recognition methods, a text-prompted recognition method, parameter/distance normalization and model adaptation techniques, and methods of updating models and a priori thresholds in speaker verification.
Book ChapterDOI
An Overview of Speaker Recognition Technology
TL;DR: This chapter overviews recent advances in speaker recognition technology and discusses general topics and issues, and more specific topics of recent interest which have led to interesting new approaches and techniques.
Journal ArticleDOI
Speaker verification: a tutorial
TL;DR: The task of speaker verification, a subset of the general problem of speaker recognition, is defined and the feature selection and pattern matching steps of the recognition procedure are examined.
References
More filters
Proceedings ArticleDOI
A vector quantization approach to speaker recognition
TL;DR: A vector quantization (VQ) codebook was used as an efficient means of characterizing the short-time spectral features of a speaker and was used to recognize the identity of an unknown speaker from his/her unlabelled spoken utterances based on a minimum distance (distortion) classification rule.
Journal ArticleDOI
Long-term feature averaging for speaker recognition
J. Markel,B. Oshika,A. Gray +2 more
TL;DR: It was demonstrated that the between-to-within speaker variance ratio was significantly increased by performing long-term averaging of the parameter sets, and the reflection coefficient averages for k 2 and k 6 were shown to produce the highest variance ratios.
Proceedings ArticleDOI
Keyword recognition using template concatenation
A. Higgins,R. Wohlford +1 more
TL;DR: A simple new KWR method is presented and the results suggest that template-concatenation KWR methods can give good results for unrestricted input speech.
Proceedings ArticleDOI
Applying matrix quantization to isolated word recognition
TL;DR: A new approach to isolated word recognition is examined, based on an extension of vector quantization speech coding, called matrix quantizationspeech coding, that was developed by Tsao and Gray.
Proceedings ArticleDOI
A realtime implementation of a text independent speaker recognition system
TL;DR: The results of this investigation clearly show that Markel's technique is superior for applications using very short speech segments for both the speaker models and the recognition trials.